LocalAI 是开源 AI 引擎。可在任意硬件上运行任何模型——LLMs、视觉、语音、图像、视频。无需 GPU。
mamba 开源项目推荐(576 个)
mamba 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 576 个仓库[CVPR 2025] MambaVision的PyTorch官方实施:Mamba-Transformer混合视觉主干
PS3控制台的扩展服务(Web服务器、https服务器、netiso、ntfs、ps3Mapi等)
Semantic Segmentation for Remote Sensing
[Mamba-Survey-2024] State-Space-Model/Mamba 及其应用的论文列表
纯锈推断引擎
[IEEE TGRS 2024] ChangeMamba: Remote Sensing Change Detection Based on Spatio-Temporal State Space Model
[NeurIPS 2024] PointMamba: A Simple State Space Model for Point Cloud Analysis
A paper list of some recent Mamba-based CV works.
Vision Mamba的实现摘自论文《Vision Mamba:双向状态空间模型的高效视觉表示学习》,它比DeiT快2.8倍,在批量推断以提取高分辨率图像特征时节省了86.8%的GPU内存
A novel implementation of fusing ViT with Mamba into a fast, agile, and high performance Multi-Modal Model. Powered by Zeta, the simplest AI framework ever.
Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
rattler-build is a universal Conda package builder for Windows, macOS and Linux (like conda-build but faster)
Reading list for research topics in state-space models
A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)
DeepTab is a Python package that simplifies tabular deep learning by providing a suite of models for regression, classification, and distributional regression tasks. It includes models such as Mambular, TabM, FT-Transformer, TabulaRNN, TabTransformer, and tabular ResNets.
Rapid builds of small Conda-based containers using micromamba.
MambaGlue:快速且稳健的本地特征匹配 Mamba @ ICRA'25
[ICLR 2024] MogaNet: Efficient Multi-order Gated Aggregation Network
Computation-Efficient Era: A Comprehensive Survey of State Space Models in Medical Image Analysis
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/mamba。
- 该话题在 GitHub 上共有 576 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 6.2 万 Star,覆盖 6 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。